Data format description for the nonlocal gravity wave parameterization dataset

Data Source

The dataset contains input and output training pairs computed using ECMWF's ERA5. The dataset was computed for the years 2010, 2012, 2014, and 2015. One month (from the validation set) is provided here for testing.

Variables Description

1. Dimensional variables: 64 latitudes (LAT) and 128 longitudes (LON)
2. features: background atmospheric state, fixed surface variables lat, lon, surface elevation and \(u, v, T, P\), concatenated along the vertical dimension.
3. output: potential temperature \(\theta \) and momentum fluxes, \(u'\omega',v'\omega'\), concatenated along the vertical dimension.

Variables Shape

1. Input shape: TIME x IDIM x LAT x LON
2. Output shape: TIME x ODIM x LAT x LON

Here, IDIM = 491, ODIM = 366, LAT=64, LON=128, TIME index ranges from 0 to 24*31 for months wth 31 days

Variables Indices

Input: has IDIM=491 (3 + 4x122) channels. It is created by concatenating the latitude (1), longitude (1), surface elevation (1), zonal winds \(u\) (122), meridional winds \(v\) (122), temperature \(T\) (122), and pressure \(P\) (122), along the vertical dimension. IDIM index 0 corresponds to latitude, 1 corresponds to longitude, 2 corresponds to surface elevation for the given latitude and longitude, 3 to 124 correspond to zonal wind, and so on.

Output: has ODIM=366 (3x122) channels. It is created by concatenating the potential temperature \(\theta\) (122), zonal flux of vertical momentum \(u'\omega'\) (122) and the meridional flux of vertical momentum \(v'\omega'\) (122) along the vertical dimension. ODIM 0 to 121 correspond to the potential temperature, and so on.

File Attributes

The netCDF attributes describe the scaling recipe for each variable. To view, execute: ncdump -h (filename)

Contact

https://github.com/amangupta2 or amangupta2@gmail.com